*THIS IS BRUTAL TO WATCH * Luke Kennard here is penalized for catching an elbow jab strike to the chest and for not simply moving out of SGA’s way.
But the best part is watching the ref not even raise his hand for the call until he realizes that SGA’s shot rolls off the rim.
BLATANT & INEXPLICABLE!
LLM Knowledge Bases
Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:
Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.
IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).
Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.
Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.
Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.
Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.
Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.
TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
There is a project on GitHub called Axios.
Axios is extremely popular. It is used by millions upon millions of applications.
Axios is a programming library that helps your JavaScript code make HTTP/S requests (communicate with websites).
In simple terms, if you're a programmer doing something with JavaScript, and want to do stuff that communicates with a website in literally any capacity, people heavily recommend using Axios due to its simplicity. Using Axios you don't have to reinvent the wheel and do a bunch of work. All you need to do is import Axios into your code and you're off to the races.
Someone (currently unknown) compromised Axios (currently unknown how) to deliver malware to people. When someone updates or installs Axios, Axios itself contains malware.
What the malware does is (currently) unknown, but it is being reversed engineered by probably every malware analyst on the planet at this moment. In a few hours more details will emerge. Information is being exchanged in real time on social media and private communication platforms as I write this.
Due to the size and popularity of Axios, it is unknown how many are impacted, it could be millions, it could be thousands, or if we're lucky, only hundreds of people or organizations will be impacted.
If this is absolute worst case scenario, millions of organizations across the planet have been infected with malware which (currently) we do not understand. However, the likelihood of this is low. It appears Axios being compromised was detected quickly, potentially within minutes (or hours) of it being compromised to deliver malware. Additionally, the likelihood of every single Axios user updating Axios as soon as it was compromised to deliver malware is astronomically low. It is basically zero.
The impact from Axios being compromised is devastating, the fallout from this will be a massive headache. This is unironically a malware nuclear missile and will likely be studied in the future.
I don't think people understand the gravity of the situation as the UN is preparing for possible nuclear weapon use in Iran.
This is a picture of Tehran. For you uneducated, untraveled, never-served, warhawks licking your chops at the thought of bombing it. It's not some low population desert. There are families, children, family pets. Regular working class people with dreams. You're sick to want war.
Tehran is a city of nearly 10,000,000 people. Imagine nuking Washington, Berlin, Paris, London, or beyond, bombed with nuclear weapons.
I gave up my diplomatic career to leak this information. I suspended my duties so as not to be part of or a witness to this crime against humanity, in an attempt to prevent a nuclear winter before it is too late.
Yesterday, nearly ten million people protested “No Kings” in the United States. The possibility of the use of nuclear weapons must be taken very seriously. It's dangerous. Act now. Spread this message worldwide. Take the streets. Protest for our humanity and future. Only the people can stop it. History will remember us.